Skip to main content
Data Science

Return to Question

deleted 1 character in body
Source Link
Ethan
Ethan
  • 1.7k
  • 9
  • 24
  • 39

I have a graph (ex: map) and multiple sequences of ids representing different paths.

  • A vertex represents a region/area
  • An edge between 2 vertices : a crossing from a region to another
  • A graph path (sequences of crossings) : a trajectory

Like the examples below  :

path1 = [15,1,2,3]
path2 = [1,2,9]
path3 = [15,3]

All the paths come from the same graph structure and they could have various high sizes (~50). Then I would like to get a low-dimensional vector (one for each path) in order to perform an Approximate Neighbors Search (it's a kind of search technique to find out the closest data points to another).

I have found some papers about graph representation learning but nothing relevant. Should I explore an NLP technique or a graph embeddings technique  ?

I have a graph (ex: map) and multiple sequences of ids representing different paths.

  • A vertex represents a region/area
  • An edge between 2 vertices : a crossing from a region to another
  • A graph path (sequences of crossings) : a trajectory

Like the examples below  :

path1 = [15,1,2,3]
path2 = [1,2,9]
path3 = [15,3]

All the paths come from the same graph structure and they could have various high sizes (~50). Then I would like to get a low-dimensional vector (one for each path) in order to perform an Approximate Neighbors Search (it's a kind of search technique to find out the closest data points to another)

I have found some papers about graph representation learning but nothing relevant. Should I explore an NLP technique or a graph embeddings technique  ?

I have a graph (ex: map) and multiple sequences of ids representing different paths.

  • A vertex represents a region/area
  • An edge between 2 vertices : a crossing from a region to another
  • A graph path (sequences of crossings) : a trajectory

Like the examples below:

path1 = [15,1,2,3]
path2 = [1,2,9]
path3 = [15,3]

All the paths come from the same graph structure and they could have various high sizes (~50). Then I would like to get a low-dimensional vector (one for each path) in order to perform an Approximate Neighbors Search (it's a kind of search technique to find out the closest data points to another).

I have found some papers about graph representation learning but nothing relevant. Should I explore an NLP technique or a graph embeddings technique?

Source Link
floriandaniel
floriandaniel
  • 11
  • 1

Low-dimensional path representation learning

I have a graph (ex: map) and multiple sequences of ids representing different paths.

  • A vertex represents a region/area
  • An edge between 2 vertices : a crossing from a region to another
  • A graph path (sequences of crossings) : a trajectory

Like the examples below :

path1 = [15,1,2,3]
path2 = [1,2,9]
path3 = [15,3]

All the paths come from the same graph structure and they could have various high sizes (~50). Then I would like to get a low-dimensional vector (one for each path) in order to perform an Approximate Neighbors Search (it's a kind of search technique to find out the closest data points to another)

I have found some papers about graph representation learning but nothing relevant. Should I explore an NLP technique or a graph embeddings technique ?